- 05 Nov, 2021 1 commit
-
-
Ignacio Rocco authored
Summary: - Old NDC convention had xy coords in [-1,1]x[-1,1] - New NDC convention has xy coords in [-1, 1]x[-u, u] or [-u, u]x[-1, 1] where u > 1 is the aspect ratio of the image. This PR fixes the NDC raysampler to use the new convention. Partial fix for https://github.com/facebookresearch/pytorch3d/issues/868 Pull Request resolved: https://github.com/fairinternal/pytorch3d/pull/29 Reviewed By: davnov134 Differential Revision: D31926148 Pulled By: bottler fbshipit-source-id: c6c42c60d1473b04e60ceb49c8c10951ddf03c74
-
- 26 Oct, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: Attempt to overcome flaky test Reviewed By: patricklabatut Differential Revision: D31895560 fbshipit-source-id: 1ecbb1782b0eafe132f88425c48487c2d0e10d2d
-
una-dinosauria authored
Summary: Make sure the functions from `rotation_conversion` are jittable, and add some type hints. Add tests to verify this is the case. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/898 Reviewed By: patricklabatut Differential Revision: D31926103 Pulled By: bottler fbshipit-source-id: bff6013c5ca2d452e37e631bd902f0674d5ca091
-
- 16 Oct, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Fix #873, that grid_sizes defaults to the wrong dtype in points2volumes code, and mask doesn't have a proper default. Reviewed By: nikhilaravi Differential Revision: D31503545 fbshipit-source-id: fa32a1a6074fc7ac7bdb362edfb5e5839866a472
-
- 11 Oct, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: PyTorch 1.6.0 came out on 28 Jul 2020. Stop builds for 1.5.0 and 1.5.1. Also update the news section of the README for recent releases. Reviewed By: nikhilaravi Differential Revision: D31442830 fbshipit-source-id: 20bdd8a07090776d0461240e71c6536d874615f6
-
- 08 Oct, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: The epsilon value is important for determining whether vertices are inside/outside a plane. Reviewed By: gkioxari Differential Revision: D31485247 fbshipit-source-id: 5517575de7c02f1afa277d00e0190a81f44f5761
-
- 07 Oct, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: Increase some test tolerances so that they pass in more situations, and re-enable two tests. Reviewed By: nikhilaravi Differential Revision: D31379717 fbshipit-source-id: 06a25470cc7b6d71cd639d9fd7df500d4b84c079
-
Ruilong Li authored
Summary: For non square image, the NDC space in pytorch3d is not square [-1, 1]. Instead, it is [-1, 1] for the smallest side, and [-u, u] for the largest side, where u > 1. This behavior is followed by the pytorch3d renderer. See the function `get_ndc_to_screen_transform` for a example. Without this fix, the rendering result is not correct using the converted pytorch3d-camera from a opencv-camera on non square images. This fix also helps the `transform_points_screen` function delivers consistent results with opencv projection for the converted pytorch3d-camera. Reviewed By: classner Differential Revision: D31366775 fbshipit-source-id: 8858ae7b5cf5c0a4af5a2af40a1358b2fe4cf74b
-
- 06 Oct, 2021 1 commit
-
-
Nikita Smetanin authored
Summary: Symmetric eigenvalues 3x3 implementation from https://github.com/fairinternal/denseposeslim/blob/roman_c3dpo/tools/functions.py#L612 based on https://en.wikipedia.org/wiki/Eigenvalue_algorithm#3.C3.973_matrices and https://www.geometrictools.com/Documentation/RobustEigenSymmetric3x3.pdf Benchmarks show significant outperformance of symeig3x3 in comparison with torch implementations (torch.symeig and torch.linalg.eigh) on GPU (P100), especially for large batches: 70-280ns per sample vs 3400ns per sample for torch_linalg_eigh_1048576_cpu It's worth mentioning that torch.linalg.eigh is still comparably fast for batches up to 8192 on CPU. Some tests are still failing as the error thresholds need to be adjusted appropriately. Reviewed By: patricklabatut Differential Revision: D29915453 fbshipit-source-id: 7c1b062da631c57c4e22a42dd0027ea5e205f1b5
-
- 02 Oct, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: New function to randomly subsample Pointclouds to a maximum size. Reviewed By: nikhilaravi Differential Revision: D30936533 fbshipit-source-id: 789eb5004b6a233034ec1c500f20f2d507a303ff
-
- 01 Oct, 2021 3 commits
-
-
Jeremy Reizenstein authored
Summary: Move the core of add_points_to_volumes to the new C++/CUDA implementation. Add new flag to let the user stop this happening. Avoids copies. About a 30% speedup on the larger cases, up to 50% on the smaller cases. New timings ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000 4575 12591 110 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000 25468 29186 20 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000 202085 209897 3 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000 46059 48188 11 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000 83759 95669 7 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000 326056 339393 2 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000 2379 4738 211 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000 12100 63099 42 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000 63323 63737 8 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000 45216 45479 12 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000 57205 58524 9 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000 139499 139926 4 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000 40129 40431 13 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000 204949 239293 3 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000 1664541 1664541 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000 391573 395108 2 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000 674869 674869 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000 2713632 2713632 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000 12726 13506 40 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000 73103 73299 7 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000 598634 598634 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000 398742 399256 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000 543129 543129 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000 1242956 1242956 1 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000 1814 8884 276 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000 1996 8851 251 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000 4608 11529 109 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000 5183 12508 97 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000 7106 14077 71 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000 25914 31818 20 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000 1778 8823 282 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000 1825 8613 274 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000 3154 10161 159 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000 4888 9404 103 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000 5194 9963 97 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000 8109 14933 62 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000 3320 10306 151 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000 7003 8595 72 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000 49140 52957 11 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000 35890 36918 14 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000 58890 59337 9 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000 286878 287600 2 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000 2484 8805 202 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000 3967 9090 127 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000 19423 19799 26 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000 33228 33329 16 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000 37292 37370 14 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000 73550 74017 7 -------------------------------------------------------------------------------- ``` Previous timings ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000 10100 46422 50 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000 28442 32100 18 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000 241127 254269 3 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000 54149 79480 10 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000 125459 212734 4 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000 512739 512739 1 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000 2866 13365 175 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000 7026 12604 72 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000 48822 55607 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000 38098 38576 14 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000 48006 54120 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000 131563 138536 4 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000 64615 91735 8 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000 228815 246095 3 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000 3086615 3086615 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000 464298 465292 2 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000 1053440 1053440 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000 6736236 6736236 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000 11940 12440 42 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000 56641 58051 9 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000 711492 711492 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000 326437 329846 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000 418514 427911 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000 1524285 1524285 1 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000 5949 13602 85 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000 5817 13001 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000 23833 25971 21 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000 9029 16178 56 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000 11595 18601 44 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000 46986 47344 11 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000 2554 9747 196 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000 2676 9537 187 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000 6567 14179 77 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000 5840 12811 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000 6102 13128 82 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000 11945 11995 42 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000 7642 13671 66 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000 25190 25260 20 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000 212018 212134 3 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000 40421 45692 13 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000 92078 92132 6 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000 457211 457229 2 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000 3574 10377 140 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000 7222 13023 70 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000 48127 48165 11 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000 34732 35295 15 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000 43050 51064 12 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000 106028 106058 5 -------------------------------------------------------------------------------- ``` Reviewed By: nikhilaravi Differential Revision: D29548609 fbshipit-source-id: 7026e832ea299145c3f6b55687f3c1601294f5c0
-
Jeremy Reizenstein authored
Summary: Added CUDA implementation to match the new, still unused, C++ function for the core of points2vols. Reviewed By: nikhilaravi Differential Revision: D29548608 fbshipit-source-id: 16ebb61787fcb4c70461f9215a86ad5f97aecb4e
-
Jeremy Reizenstein authored
Summary: Single C++ function for the core of points2vols, not used anywhere yet. Added ability to control align_corners and the weight of each point, which may be useful later. Reviewed By: nikhilaravi Differential Revision: D29548607 fbshipit-source-id: a5cda7ec2c14836624e7dfe744c4bbb3f3d3dfe2
-
- 30 Sep, 2021 3 commits
-
-
Jeremy Reizenstein authored
Summary: Allow saving colors as 8bit when writing .ply files. Reviewed By: patricklabatut, nikitos9000 Differential Revision: D30905312 fbshipit-source-id: 44500982c9ed6d6ee901e04f9623e22792a0e7f7
-
Nikhila Ravi authored
Summary: CUDA implementation of 3D bounding box overlap calculation. Reviewed By: gkioxari Differential Revision: D31157919 fbshipit-source-id: 5dc89805d01fef2d6779f00a33226131e39c43ed
-
Nikhila Ravi authored
Summary: C++ Implementation of algorithm to compute 3D bounding boxes for batches of bboxes of shape (N, 8, 3) and (M, 8, 3). Reviewed By: gkioxari Differential Revision: D30905190 fbshipit-source-id: 02e2cf025cd4fa3ff706ce5cf9b82c0fb5443f96
-
- 29 Sep, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: I have implemented an exact solution for 3D IoU of oriented 3D boxes. This file includes: * box3d_overlap: which computes the exact IoU of box1 and box2 * box3d_overlap_sampling: which computes an approximate IoU of box1 and box2 by sampling points within the boxes Note that both implementations currently do not support batching. Our exact IoU implementation is based on the fact that the intersecting shape of the two 3D boxes will be formed by segments of the surface of the boxes. Our algorithm computes these segments by reasoning whether triangles of one box are within the second box and vice versa. We deal with intersecting triangles by clipping them. Reviewed By: gkioxari Differential Revision: D30667497 fbshipit-source-id: 2f747f410f90b7f854eeaf3036794bc3ac982917
-
- 23 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Attempt to fix #659, an observation that the rasterizer is nondeterministic, by resolving tied faces by picking those with lower index. Reviewed By: nikhilaravi, patricklabatut Differential Revision: D30699039 fbshipit-source-id: 39ed797eb7e9ce7370ae71259ad6b757f9449923
-
- 15 Sep, 2021 3 commits
-
-
Nikhila Ravi authored
Summary: CUDA implementation of farthest point sampling algorithm. ## Visual comparison Compared to random sampling, farthest point sampling gives better coverage of the shape. {F658631262} ## Reduction Parallelized block reduction to find the max value at each iteration happens as follows: 1. First split the points into two equal sized parts (e.g. for a list with 8 values): `[20, 27, 6, 8 | 11, 10, 2, 33]` 2. Use half of the thread (4 threads) to compare pairs of elements from each half (e.g elements [0, 4], [1, 5] etc) and store the result in the first half of the list: `[20, 27, 6, 33 | 11, 10, 2, 33]` Now we no longer care about the second part but again divide the first part into two `[20, 27 | 6, 33| -, -, -, -]` Now we can use 2 threads to compare the 4 elements 4. Finally we have gotten down to a single pair `[20 | 33 | -, - | -, -, -, -]` Use 1 thread to compare the remaining two elements 5. The max will now be at thread id = 0 `[33 | - | -, - | -, -, -, -]` The reduction will give the farthest point for the selected batch index at this iteration. Reviewed By: bottler, jcjohnson Differential Revision: D30401803 fbshipit-source-id: 525bd5ae27c4b13b501812cfe62306bb003827d2 -
Nikhila Ravi authored
Summary: C++ implementation of iterative farthest point sampling. Reviewed By: jcjohnson Differential Revision: D30349887 fbshipit-source-id: d25990f857752633859fe00283e182858a870269
-
Nikhila Ravi authored
Summary: This is a naive python implementation of the iterative farthest point sampling algorithm along with associated simple tests. The C++/CUDA implementations will follow in subsequent diffs. The algorithm is used to subsample a pointcloud with better coverage of the space of the pointcloud. The function has not been added to `__init__.py`. I will add this after the full C++/CUDA implementations. Reviewed By: jcjohnson Differential Revision: D30285716 fbshipit-source-id: 33f4181041fc652776406bcfd67800a6f0c3dd58
-
- 13 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Fix issue #826. This is a correction to the joining of TexturesUV into a single scene. Reviewed By: nikhilaravi Differential Revision: D30767092 fbshipit-source-id: 03ba6a1d2f22e569d1b3641cd13ddbb8dcb87ec7
-
- 10 Sep, 2021 1 commit
-
-
Shangchen Han authored
Summary: * HAT_INV_SKEW_SYMMETRIC_TOL was a global variable and torch script gives an error when compiling that function. Move it to the function scope. * torch script gives error when compiling acos_linear_extrapolation because bound is a union of tuple and float. The tuple version is kept in this diff. Reviewed By: patricklabatut Differential Revision: D30614916 fbshipit-source-id: 34258d200dc6a09fbf8917cac84ba8a269c00aef
-
- 09 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: In D30349234 (https://github.com/facebookresearch/pytorch3d/commit/1b8d86a104eab24ac25863c423d084d611f64bae) we introduced persistent=False to some register_buffer calls, which depend on PyTorch 1.6. We go back to the old behaviour for PyTorch 1.5. Reviewed By: nikhilaravi Differential Revision: D30731327 fbshipit-source-id: ab02ef98ee87440ef02479b72f4872b562ab85b5
-
- 02 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Change cyclic deps test to be independent of test discovery order. Also let it work without plotly. Reviewed By: nikhilaravi Differential Revision: D30669614 fbshipit-source-id: 2eadf3f8b56b6096c5466ce53b4f8ac6df27b964
-
- 01 Sep, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: Fixes GitHub issue #751. The vectorized implementation of bilinear interpolation didn't properly handle the edge cases in the same way as the `grid_sample` method in PyTorch. Reviewed By: bottler Differential Revision: D30684208 fbshipit-source-id: edf241ecbd72d46b94ad340a4e601e26c83db88e
-
- 31 Aug, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: As suggested in #802. By not persisting the _xy_grid buffer, we can allow (in some cases) a model with one image_size to be loaded from a saved model which was trained at a different resolution. Also avoid persisting _frequencies in HarmonicEmbedding for similar reasons. BC-break: This will cause load_state_dict, in strict mode, to complain if you try to load an old model with the new code. Reviewed By: patricklabatut Differential Revision: D30349234 fbshipit-source-id: d6061d1e51c9f79a78d61a9f732c9a5dfadbbb47
-
Jeremy Reizenstein authored
Summary: Use PyTorch3D's new faster sample_pdf function instead of local Python implementation. Also clarify deps for the Python implementation. Reviewed By: gkioxari Differential Revision: D30512109 fbshipit-source-id: 84cfdc00313fada37a6b29837de96f6a4646434f
-
- 23 Aug, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: New test that each subpackage of pytorch3d imports cleanly. Reviewed By: patricklabatut Differential Revision: D30001632 fbshipit-source-id: ca8dcac94491fc22f33602b3bbef481cba927094
-
- 17 Aug, 2021 5 commits
-
-
Jeremy Reizenstein authored
Summary: Implement the sample_pdf function from the NeRF project as compiled operators.. The binary search (in searchsorted) is replaced with a low tech linear search, but this is not a problem for the envisaged numbers of bins. Reviewed By: gkioxari Differential Revision: D26312535 fbshipit-source-id: df1c3119cd63d944380ed1b2657b6ad81d743e49
-
Jeremy Reizenstein authored
Summary: Copy the sample_pdf operation from the NeRF project in to PyTorch3D, in preparation for optimizing it. Reviewed By: gkioxari Differential Revision: D27117930 fbshipit-source-id: 20286b007f589a4c4d53ed818c4bc5f2abd22833
-
Jeremy Reizenstein authored
Summary: Add a CPU version to the benchmarks. ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000 10100 46422 50 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000 28442 32100 18 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000 241127 254269 3 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000 54149 79480 10 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000 125459 212734 4 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000 512739 512739 1 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000 2866 13365 175 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000 7026 12604 72 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000 48822 55607 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000 38098 38576 14 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000 48006 54120 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000 131563 138536 4 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000 64615 91735 8 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000 228815 246095 3 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000 3086615 3086615 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000 464298 465292 2 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000 1053440 1053440 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000 6736236 6736236 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000 11940 12440 42 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000 56641 58051 9 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000 711492 711492 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000 326437 329846 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000 418514 427911 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000 1524285 1524285 1 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000 5949 13602 85 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000 5817 13001 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000 23833 25971 21 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000 9029 16178 56 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000 11595 18601 44 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000 46986 47344 11 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000 2554 9747 196 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000 2676 9537 187 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000 6567 14179 77 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000 5840 12811 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000 6102 13128 82 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000 11945 11995 42 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000 7642 13671 66 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000 25190 25260 20 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000 212018 212134 3 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000 40421 45692 13 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000 92078 92132 6 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000 457211 457229 2 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000 3574 10377 140 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000 7222 13023 70 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000 48127 48165 11 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000 34732 35295 15 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000 43050 51064 12 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000 106028 106058 5 -------------------------------------------------------------------------------- ``` Reviewed By: patricklabatut Differential Revision: D29522830 fbshipit-source-id: 1e857db03613b0c6afcb68a58cdd7ba032e1a874
-
Jeremy Reizenstein authored
Summary: Fixes to a couple of comments on points to volumes, make the mask work in round_points_to_volumes, and remove a duplicate rand calculation Reviewed By: nikhilaravi Differential Revision: D29522845 fbshipit-source-id: 86770ba37ef3942b909baf63fd73eed1399635b6
-
Jeremy Reizenstein authored
Summary: Much of the code is actually available during the conda tests, as long as we look in the right place. We enable some of them. Reviewed By: nikhilaravi Differential Revision: D30249357 fbshipit-source-id: 01c57b6b8c04442237965f23eded594aeb90abfb
-
- 12 Aug, 2021 2 commits
-
-
Nikhila Ravi authored
Summary: Implementation of ball query from PointNet++. This function is similar to KNN (find the neighbors in p2 for all points in p1). These are the key differences: - It will return the **first** K neighbors within a specified radius as opposed to the **closest** K neighbors. - As all the points in p2 do not need to be considered to find the closest K, the algorithm is much faster than KNN when p2 has a large number of points. - The neighbors are not sorted - Due to the radius threshold it is not guaranteed that there will be K neighbors even if there are more than K points in p2. - The padding value for `idx` is -1 instead of 0. # Note: - Some of the code is very similar to KNN so it could be possible to modify the KNN forward kernels to support ball query. - Some users might want to use kNN with ball query - for this we could provide a wrapper function around the current `knn_points` which enables applying the radius threshold afterwards as an alternative. This could be called `ball_query_knn`. Reviewed By: jcjohnson Differential Revision: D30261362 fbshipit-source-id: 66b6a7e0114beff7164daf7eba21546ff41ec450
-
Jeremy Reizenstein authored
Summary: New test that notes and tutorials are listed in the website metadata, so that they will be included in the website build. Reviewed By: nikhilaravi Differential Revision: D30223799 fbshipit-source-id: 2dca9730b54e68da2fd430a7b47cb7e18814d518
-
- 09 Aug, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: Fix to resolve GitHub issue #796 - the cameras were being passed in the renderer forward pass instead of at initialization. The rasterizer was correctly using the cameras passed in the `kwargs` for the projection, but the `cameras` are still part of the `kwargs` for the `get_screen_to_ndc_transform` and `get_ndc_to_screen_transform` functions which is causing issues about duplicate arguments. Reviewed By: bottler Differential Revision: D30175679 fbshipit-source-id: 547e88d8439456e728fa2772722df5fa0fe4584d
-
- 02 Aug, 2021 1 commit
-
-
Georgia Gkioxari authored
Summary: API fix for NDC/screen cameras and compatibility with PyTorch3D renderers. With this new fix: * Users can define cameras and `transform_points` under any coordinate system conventions. The transformation applies the camera K and RT to the input points, not regarding for PyTorch3D conventions. So this makes cameras completely independent from PyTorch3D renderer. * Cameras can be defined either in NDC space or screen space. For existing ones, FoV cameras are in NDC space. Perspective/Orthographic can be defined in NDC or screen space. * The interface with PyTorch3D renderers happens through `transform_points_ndc` which transforms points to the NDC space and assumes that input points are provided according to PyTorch3D conventions. * Similarly, `transform_points_screen` transforms points to screen space and again assumes that input points are under PyTorch3D conventions. * For Orthographic/Perspective cameras, if they are defined in screen space, the `get_ndc_camera_transform` allows points to be converted to NDC for use for the renderers. Reviewed By: nikhilaravi Differential Revision: D26932657 fbshipit-source-id: 1a964e3e7caa54d10c792cf39c4d527ba2fb2e79
-
- 19 Jul, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: A bad env var check meant these tests were not being run. Fix that, and fix the copyright test for the new message format. Reviewed By: patricklabatut Differential Revision: D29734562 fbshipit-source-id: a1a9bb68901b09c71c7b4ff81a04083febca8d50
-
Alexey Sidnev authored
Summary: # Background There is an unstable error during training (it can happen after several minutes or after several hours). The error is connected to `torch.det()` function in `_check_valid_rotation_matrix()`. if I remove the function `torch.det()` in `_check_valid_rotation_matrix()` or remove the whole functions `_check_valid_rotation_matrix()` the error is disappeared (D29555876). # Solution Replace `torch.det()` with manual implementation for 3x3 matrix. Reviewed By: patricklabatut Differential Revision: D29655924 fbshipit-source-id: 41bde1119274a705ab849751ece28873d2c45155
-
